As technology has a great impact in our current
lifestyle compared to old times, plagiarism is a phenomenon
that is increasing day by day. The effect of the pandemic
Covid-19 even moved into online space.. Students complete
their assignments independently, at the same time another
part of students either copy from others or download from
the internet. In case of textual works detection process is easy
and some of the system already exists.. But students mask
plagiarism by changing the order, shuffling contents, changing
the structure and other similar things. We are trying to find a
solution for this type of problem and make it very low cost.
Here we propose a system that finds the similarity between
the given document images which can either be a text
document or a handwritten text image, find the similarity
score between them using the cosine similarity method, and
determine whether the submitted documents are plagiarized
or not or is it similar to the submitted text images. In this way,
teachers can easily determine whether a particular text
document with images has been plagiarized.. To identify the
text from the image we use the OCR technique.
Keywords : Plagiarism System, Text mining, Data Mining.